
Sauna reads the claim file, policy, and adjuster notes, drafts the coverage analysis, builds the reserve worksheet, and writes the denial or settlement letter for your sign-off before anything goes to the insured.
What it does
Sauna pulls the policy form and loss facts from the claim record in Salesforce, drafts a coverage position memo citing the exact exclusions and endorsements, and flags where the file is missing proof of loss.
It assembles the estimate, medicals, and prior payments into a reserve calculation in Google Sheets, shows the math, and notes which line items still need a vendor quote.
Sauna writes the reservation-of-rights, status-update, or settlement letter in Google Docs, pulling claim numbers and dates from the file, and holds it for your review before it sends.
It tracks outstanding documents and adjuster diary dates in Asana and drafts the follow-up emails to the insured, body shop, or treating provider so nothing ages past your service standard.
Put Sauna to work on this.
Get started for freeIn context
Sauna shows up where you already work — the web app, Slack, email, iMessage, and Superhuman. It reads what it needs, does the task, and comes back with the draft for your approval.
Try it
The literal prompt for this job. Open it in Sauna and it picks up from there.
“Read claim 48213 — the policy, the estimate, and my notes. Draft a coverage analysis on the water-damage exclusion and a reserve worksheet, and flag what's still missing.”
Plugs into the tools you already run — and thousands more, or any MCP server.
Good to know
No. It drafts a coverage position from the policy language and loss facts in the file and cites the clauses it relied on. The coverage call and every letter to the insured wait for your approval.
No. Reserve figures come only from the estimate, medicals, and payments already in the claim record. It shows the arithmetic and marks any line item that has no supporting document.
Sauna reads only what you connect, and acts only after you approve. Your workspace and its memory are yours, not training data.
Keep exploring